检索结果-内蒙古大学图书馆

17th International Conference on Parallel Problem Solving from Nature (PPSN)

作者： Bentley, Peter J. Lim, Soo Ling Gaier, Adam Linh Tran Univ Coll London UCL Dept Comp Sci London England Autodesk Res London England

ISBN: (纸本)9783031147142;9783031147135

Nature has spent billions of years perfecting our genetic representations, making them evolvable and expressive. Generative machine learning offers a shortcut: learn an evolvable latent space with implicit biases towards better solutions. We present SOLVE: Search space Optimization with Latent Variable Evolution, which creates a dataset of solutions that satisfy extra problem criteria or heuristics, generates a new latent search space, and uses a genetic algorithm to search within this new space to find solutions that meet the overall objective. We investigate SOLVE on five sets of criteria designed to detrimentally affect the search space and explain how this approach can be easily extended as the problems become more complex. We show that, compared to an identical GA using a standard representation, SOLVE with its learned latent representation can meet extra criteria and find solutions with distance to optimal up to two orders of magnitude closer. We demonstrate that SOLVE achieves its results by creating better search spaces that focus on desirable regions, reduce discontinuities, and enable improved search by the genetic algorithm.

关键词： variational autoencoder Latent variable evolution Generative machine learning Genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Toward a better monitoring statistic for profile monitoring via variational autoencoders

引用

JOURNAL OF QUALITY TECHNOLOGY 2021年第5期53卷 454-473页

作者： Sergin, Nurettin Dorukhan Yan, Hao Arizona State Univ Ind Engineer Program Tempe AZ USA Arizona State Univ Tempe AZ 85287 USA

variational autoencoders have been recently proposed for the problem of process monitoring. While these works show impressive results over classical methods, the proposed monitoring statistics often ignore the inconsistencies in learned lower-dimensional representations and computational limitations in high-dimensional approximations. In this work, we first manifest these issues and then overcome them with a novel statistic formulation that increases out-of-control detection accuracy without compromising computational efficiency. We demonstrate our results on a simulation study with explicit control over latent variations, and a real-life example of image profiles obtained from a hot steel rolling process.

关键词： Deep learning high-dimensional nonlinear profile latent variable model profile monitoring variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Expediting structure-property analyses using variational autoencoders with regression

引用

COMPUTATIONAL MATERIALS SCIENCE 2024年 242卷

作者： Templeton, William Frieden Miner, Justin P. Ngo, Austin Fitzwater, Lauren Reddy, Tharun Abranovic, Brandon Prichard, Paul Lewandowski, John J. Narra, Sneha Prabha Carnegie Mellon Univ Dept Mech Engn 5000 Forbes Ave Pittsburgh PA 15213 USA Case Western Reserve Univ Dept Mat Sci & Engn 10900 Euclid Ave Cleveland OH 44106 USA Carnegie Mellon Univ Dept Mat Sci & Engn 5000 Forbes Ave Pittsburgh PA 15213 USA Kennametal Inc 1600 Technol Way Latrobe PA 15650 USA

We present a machine learning approach that expedites structure-property analysis in materials, bypassing traditional feature extraction and exploratory data analysis techniques. This objective is accomplished by employing a variational autoencoder (VAE) structure that is modified to include a regressor network for property prediction (VAE-Regression). This modification allows for direct linkage of imaged features and quantitative part properties within the VAE latent space. We first demonstrate our approach using 2D optical micrographs and corresponding four -point bend fatigue life data from laser beam powder bed fusion additively manufactured Ti-6Al-4V coupons. The VAE-Regression model extracts spatial features, predicts fatigue life, and identifies features of porosity defect governing fatigue behavior such as pore clusters, pores near sample edges, and jagged pore morphologies. These features corroborate fatigue literature on physics -based modeling and experimentation. We then demonstrate the versatility of our methodology using binder jet additively manufactured WC -Co coupons, where porosity and microstructural discontinuities are known to lower the three-point bend transverse rupture strength, but the interaction between the WC and Co are yet to be completely understood. We attempted to understand these interactions using our VAE-Regression architecture. Within our dataset, we show that coarser WC grains surrounded by larger Co pools indicate lower strength, while finer WC grains with smaller Co pools indicate higher strength. This machine learning approach using image -based data will likely prove to be critical in understanding and identifying structure-property relationships in new materials and manufacturing processes.

关键词： variational autoencoder Probabilistic modeling Additive manufacturing Regression structure-property relationship Feature vector representation

来源：评论

学校读者我要写书评

暂无评论

Achieving explainability for plant disease classification with disentangled variational autoencoders

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年第PartA期133卷

作者： Habaragamuwa, Harshana Oishi, Yu Tanaka, Kenichi Natl Agr & Food Res Org NARO Tsukuba Japan Natl Agr & Food Res Org Res Ctr Agr Informat Technol Core Technol Res Headquarters 1-31-1 Kannondai Tsukuba Ibaraki 3050856 Japan

Agricultural image recognition tasks are becoming increasingly dependent on systems based on deep learning (DL);however, despite the excellent performance of DL, it is difficult to comprehend the type of logic or features of the input image it uses during decision making. Knowing the logic or features is highly crucial for result verification, algorithm improvement, training data improvement, and knowledge extraction. However, the explanations from the current heatmap-based algorithms are insufficient for the abovementioned requirements. To address this, this paper details the development of a classification and explanation method based on a variational autoencoder (VAE) architecture, which can visualize the variations of the most important features by visualizing the generated images that correspond to the variations of those features. Using the PlantVillage dataset, an acceptable level of explainability was achieved without sacrificing the classification accuracy. The proposed method can also be extended to other crops as well as other image classification tasks. Further, application systems using this method for disease identification tasks, such as the identification of potato blackleg disease, potato virus Y, and other image classification tasks, are currently being developed.

关键词： Explainable deep learning variational autoencoder Feature visualization Disentangled representation Crop disease classification

来源：评论

学校读者我要写书评

暂无评论

Unsupervised anomaly detection for multilevel converters based on wavelet transform and variational autoencoders

Unsupervised anomaly detection for multilevel converters bas...

引用

14th Annual IEEE Energy Conversion Congress and Exposition (IEEE ECCE) / IEEE-Industry-Applications-Society (IEEE-IAS) Annual Meeting

作者： Ye, Shu Zhang, Feng Shanghai Jiao Tong Univ Dept Elect Informat & Elect Engn Shanghai Peoples R China

ISBN: (数字)9781728193878

ISBN: (纸本)9781728193878

This paper proposes an anomaly detection scheme for multilevel converters based on a wavelet packet transform and variational autoencoder (WPT-VAE). The wavelet packet transform is used for dimensionality reduction and feature extraction of raw signals. The extracted features are normalized and then sent to the VAE to perform further feature extraction and waveform regeneration. Based on a five-level nested neutral-point-piloted (NNPP) converter, the effectiveness of the proposed method is verified by experiments. The normal dataset is used for model training, while a mixed dataset composed of normal and abnormal data is used for testing. The results show that the proposed WPT-VAE exhibits superior performances in anomaly detection compared with a widely used classification algorithm. Abnormal data can be quickly and accurately distinguished from normal data for early intervention to prevent serious faults, which has good practical value.

关键词： fault diagnosis anomaly detection multilevel converters variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Multimodal Disentanglement variational autoencoders for Zero-Shot Cross-Modal Retrieval 22

Multimodal Disentanglement Variational AutoEncoders for Zero...

引用

45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

作者： Tian, Jialin Wang, Kai Xu, Xing Cao, Zuo Shen, Fumin Shen, Heng Tao Univ Elect Sci & Technol China Ctr Future Media Chengdu Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu Peoples R China Meituan Shanghai Peoples R China Koala Uran Technol Ltd Chengdu Peoples R China Peng Cheng Lab Shenzhen Peoples R China

ISBN: (纸本)9781450387323

Zero-Shot Cross-Modal Retrieval (ZS-CMR) has recently drawn increasing attention as it focuses on a practical retrieval scenario, i.e, the multimodal test set consists of unseen classes that are disjoint with seen classes in the training set. The recently proposed methods typically adopt the generative model as the main framework to learn a joint latent embedding space to alleviate the modality gap. Generally, these methods largely rely on auxiliary semantic embeddings for knowledge transfer across classes and unconsciously neglect the effect of the data reconstruction manner in the adopted generative model. To address this issue, we propose a novel ZS-CMR model termed Multimodal Disentanglement variational autoencoders (MD-VAE), which consists of two coupled disentanglement variational autoencoders (DVAEs) and a fusion-exchange VAE (FVAE). Specifically, DVAE is developed to disentangle the original representations of each modality into modality-invariant and modality-specific features. FVAE is designed to fuse and exchange information of multimodal data by the reconstruction and alignment process without pre-extracted semantic embeddings. Moreover, an advanced counter-intuitive cross-reconstruction scheme is further proposed to enhance the informativeness and generalizability of the modality-invariant features for more effective knowledge transfer. The comprehensive experiments on four image-text retrieval and two image-sketch retrieval datasets consistently demonstrate that our method establishes the new state-of-the-art performance.

关键词： Cross-Modal Retrieval Zero-Shot Learning Disentanglement Reconstruction variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Generating NLFM Radar Waveforms using variational autoencoders

Generating NLFM Radar Waveforms using Variational Autoencode...

引用

IEEE Radar Conference (RadarConf)

作者： Charlish, Alexander Schwalm, Carolin Fraunhofer FKIE Sensor Data & Informat Fus Dept D-53343 Wachtberg Germany

ISBN: (纸本)9781728153681

The rapid synthesis of radar waveform modulations is key to enabling a radar to react to the environment in order to optimize performance. This paper proposes the use of generative models for radar waveform generation. Specifically, variational autoencoders (VAEs) comprising neural networks that are trained with a novel reconstruction loss are proposed. It is shown for simple classes of non-linear FM waveforms that the decoder from the proposed VAE can generate new radar waveform modulations that possess required ambiguity function characteristics, even though they were not represented in the training data.

关键词： Waveform diversity cognitive radar radar waveform synthesis generative models variational autoencoder neural networks machine learning artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Enabling Feedback-Free MIMO Transmission for FD-RAN: A Data-Driven Approach

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2025年第3期24卷 2437-2454页

作者： Liu, Jingbo Chen, Jiacheng Liu, Zongxi Zhou, Haibo Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai 200240 Peoples R China Pengcheng Lab Shenzhen 518000 Peoples R China Pengcheng Lab Dept Strateg & Adv Interdisciplinary Res Shenzhen 518000 Peoples R China Nanjing Univ Sch Elect Sci & Engn Nanjing 210023 Peoples R China

To enhance flexibility and facilitate resource cooperation, a novel fully-decoupled radio access network (FD-RAN) architecture is proposed for 6G. However, the decoupling of uplink (UL) and downlink (DL) in FD-RAN makes the existing feedback mechanism ineffective. To this end, we propose an end-to-end data-driven MIMO solution without the conventional channel feedback procedure. Data-driven MIMO can alleviate the drawbacks of feedback including overheads and delay, and can provide customized precoding design for different BSs based on their historical channel data. It essentially learns a mapping from geolocation to MIMO transmission parameters. We first present a codebook-based approach, which selects transmission parameters from the statistics of discrete channel state information (CSI) values and utilizes nearest neighbor interpolation for spatial inference. We further present a non-codebook-based approach, which 1) derives the optimal precoder from the singular value decomposition (SVD) of the channel;2) utilizes variational autoencoder (VAE) to select the representative precoder from the latent Gaussian representations;and 3) exploits Gaussian process regression (GPR) to predict unknown precoders in the space domain. Extensive simulations are performed on a link-level 5G simulator using realistic ray-tracing channel data. The results demonstrate the effectiveness of data-driven MIMO, showcasing its potential for application in FD-RAN and 6G.

关键词： 6G fully-decoupled RAN MIMO codebook variational autoencoder 6G fully-decoupled RAN MIMO codebook variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

DP-VAE: Human-Readable Text Anonymization for Online Reviews with Differentially Private variational autoencoders 22

DP-VAE: Human-Readable Text Anonymization for Online Reviews...

引用

31st ACM Web Conference (WWW)

作者： Weggenmann, Benjamin Rublack, Valentin Andrejczuk, Michael Mattern, Justus Kerschbaum, Florian SAP Secur Res Karlsruhe Germany Univ Edinburgh Edinburgh Scotland Univ Waterloo Waterloo ON Canada

ISBN: (纸本)9781450390965

While vast amounts of personal data are shared daily on public online platforms and used by companies and analysts to gain valuable insights, privacy concerns are also on the rise: Modern authorship attribution techniques have proven effective at identifying individuals from their data, such as their writing style or behavior of picking and judging movies. It is hence crucial to develop data sanitization methods that allow sharing of users' data while protecting their privacy and preserving quality and content of the original data. In this paper, we tackle anonymization of textual data and propose an end-to-end differentially private variational autoencoder architecture. Unlike previous approaches that achieve differential privacy on a per-word level through individual perturbations, our solution works at an abstract level by perturbing the latent vectors that provide a global summary of the input texts. Decoding an obfuscated latent vector thus not only allows our model to produce coherent, high-quality output text that is human-readable, but also results in strong anonymization due to the diversity of the produced data. We evaluate our approach on IMDb movie and Yelp business reviews, confirming its anonymization capabilities and preservation of the semantics and utility of the original sentences.

关键词： differential privacy text anonymization variational autoencoder adversarial autoencoder disentangled representations authorship obfuscation authorship attribution online reviews

来源：评论

学校读者我要写书评

暂无评论

Scalable variational quantum circuits for autoencoder-based drug discovery 22

Scalable variational quantum circuits for autoencoder-based ...

引用

Proceedings of the 2022 Conference & Exhibition on Design, Automation & Test in Europe

作者： Junde Li Swaroop Ghosh The Pennsylvania State University

ISBN: (纸本)9783981926361

The de novo design of drug molecules is recognized as a time-consuming and costly process, and computational approaches have been applied in each stage of the drug discovery pipeline. variational autoencoder is one of the computer-aided design methods which explores the chemical space based on an existing molecular dataset. Quantum machine learning has emerged as an atypical learning method that may speed up some classical learning tasks because of its strong expressive power. However, near-term quantum computers suffer from limited number of qubits which hinders the representation learning in high dimensional spaces. We present a scalable quantum generative autoencoder (SQ-VAE) for simultaneously reconstructing and sampling drug molecules, and a corresponding vanilla variant (SQ-AE) for better reconstruction. The architectural strategies in hybrid quantum classical networks such as, adjustable quantum layer depth, heterogeneous learning rates, and patched quantum circuits are proposed to learn high dimensional dataset such as, ligand-targeted drugs. Extensive experimental results are reported for different dimensions including 8x8 and 32x32 after choosing suitable architectural strategies. The performance of quantum generative autoencoder is compared with the corresponding classical counterpart throughout all experiments. The results show that quantum computing advantages can be achieved for normalized low-dimension molecules, and that high-dimension molecules generated from quantum generative autoencoders have better drug properties within the same learning period.

关键词： drug discovery quantum machine learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：